Every morning the desk deals pitch slips from the client’s own brand brain — topic, platform, format, and the reason it’s on the pile. Take one and it lands on the calendar briefed. Dismiss one three times and the theme is retired.
Suggestions on every plan · credit-metered — the estimate shows before you run
Ideas argued from their knowledge base — not a trending-topics feed.
Why now: core theme, weight 0.8 · no LinkedIn post in 6 days · educate pillar underfed
Why now: carousel format unused this fortnight · Instagram slot open Thursday
Why now: persona “the ingredient checker” unserved this month
The desk stops pitching what you keep spiking — that’s real, and it’s the one learning signal we claim.
Pitches aren’t random and they aren’t trending-topic scrapes — every slip traces back to the client’s own knowledge base and survives four editorial filters before it reaches you.
The knowledge base is distilled into weighted core themes per client — pitches draw from the map, so a skincare brand gets barrier science, not generic “5 productivity hacks”.
The desk scans the client’s calendar for empty weekdays and underfed platforms and pitches straight into the holes — the “why now” on the slip is a real gap, not decoration.
Editorial filters enforce format diversity and platform rotation — an unused platform gets a boost, near-duplicate ideas get merged, and the pile stays worth reading.
Dismiss a pitch and it’s remembered. Dismiss the same theme three times and the desk retires it — the one learning behaviour here we claim, because it’s the one that exists.
Published posts report their engagement back, and three instruments read it. Each one switches on at a printed threshold — because statistics on four posts would be astrology, and we’d rather show you the gate than fake the wisdom.
Before a post ships, its predicted engagement rate is banded from your own history — hook style, length, day, quality score. A rate, honestly — never a promised reach number.
Real correlation math checks which quality dimensions actually predict engagement for this client — and re-weights the score only when the evidence clears the bar.
Post the same keyword often enough and the instrument watches the trend — a real decline flags the topic before the audience files the complaint.
Straight answer: these instruments calibrate the quality score and your judgement — they don’t currently steer which topics the pitch desk deals. Two desks, side by side. If we wire them together, the changelog says so first.
The scoring gate itself lives on the AI Pipeline pageToday the pitch desk learns from one signal: your dismissals. It does not yet learn from what you use, save, or edit — plenty of tools imply otherwise about themselves; we’d rather under-claim and ship the rest later.
Predictions are engagement-rate bands from your own history, and they need about ten published posts before they say anything at all. “Learns over time” is the claim — not a crystal ball.
The morning pile is dealt
Start free with 2,000 credits — paste a client’s URL and the desk starts pitching from their world the same day. Roughly a week of real production, on us.
No card · No trial countdown · No per-client fees